Kristopher-Chen

HifiGAN training -- obvious harmonics in test files

7

I trained HifiGAN on VCTK multi-speaker datasets with 24kHz sampling rate. I also do normalization in the input log-Mel spectrogram (with mean=-4, std=4)， and found obvious harmonics in the test...

Any to many vc, how to improve the speech intelligence for arbitrary inputs？

16

When testing arbitrary inputs for any-to-many vc cases, the speech intelligence sometimes drops, where some phonemes cannot be well pronounced or sounds blur. It seems there are no other explicit...

Concatenate Error

3

Hi, have you ever met this problem? in "training_tf2/lpcnet.py", line 246, in new_lpcnet_model, ValueError: A `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes:...

Hi, when I tried to extract with mels in the order of 16, clipping happens. If I make a threshold in the Levison Durbin function, it got better. but when...

Difference between SSL and PPG-based methods?

1

Hi, I really appreciate your work; the demo sounds great. I also read papers about PPG-based VC, which uses ASR for PPG extraction. I just wonder about the difference between...

Mdense layer without softmax and bad testing samplies

1

When checking the code, I find Mdense layer without softmax with a little different from the official code. And when testing, bad samples are generated. Have you ever met with...